This paper describes a method for recognizing Japanese handwritten characters including touching ones. The touching characters are segmented by cutting the connected components in the presegmentation process. The proposed segmentation method consists of the following steps: (1) identification of the touching components by checking the size of character candidate patterns, (2) estimation of the break point and cutting of the components, and (3) generation of character candidate patterns by merging the components with adjacent patterns. The proposed method has the feature that the touching components could be identified even if they are comprised in relatively small patterns. The touching components are to be cut by the stroke width analysis and by the projection image analysis. This cut and merge procedure could segment 134 (88.2%) address lines correctly, out of 152 Japanese address lines having touching portions, and could generate correct character candidate patterns.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.